[CUDA] Driver changes to pass flags needed to use detected CUDA installation.

[tra]

Summary

• added include paths to detected CUDA installation
• added include paths for -aux-triple
• added -nocudainc to prevent addition of CUDA include path.
• added test cases to verify new functionality

[tra]

Updated to reflect latest changes in D13144

[tra]

Moved libdevice detection and linking into a separate patch D14556.

[echristo]

This needs a very long commit message describing exactly what's going on and why since it's not documented anywhere. Possibly in the code as well at AddPreprocessingOptions and other places you add AuxToolChain. Some of this is going to need to get refactored in the medium term when we look at being able to preprocess and add multiple target argument passing, but this is an ok intermediate step.

Thanks!

-eric

cfe/trunk/include/clang/Driver/Options.td

 def no_canonical_prefixes : Flag<["-"], "no-canonical-prefixes">, Flags<[HelpHidden]>,
   HelpText<"Use relative instead of canonical paths">;
 def no_cpp_precomp : Flag<["-"], "no-cpp-precomp">, Group<clang_ignored_f_Group>;
 def no_integrated_cpp : Flag<["-", "--"], "no-integrated-cpp">, Flags<[DriverOption]>;
 def no_pedantic : Flag<["-", "--"], "no-pedantic">, Group<pedantic_Group>;
 def no__dead__strip__inits__and__terms : Flag<["-"], "no_dead_strip_inits_and_terms">;
 def nobuiltininc : Flag<["-"], "nobuiltininc">, Flags<[CC1Option]>,
   HelpText<"Disable builtin #include directories">;
+def nocudainc : Flag<["-"], "nocudainc">;
 def nodefaultlibs : Flag<["-"], "nodefaultlibs">;
 def nofixprebinding : Flag<["-"], "nofixprebinding">;
 def nolibc : Flag<["-"], "nolibc">;
 def nomultidefs : Flag<["-"], "nomultidefs">;
 def nopie : Flag<["-"], "nopie">;
 def noprebind : Flag<["-"], "noprebind">;
 def noseglinkedit : Flag<["-"], "noseglinkedit">;
 def nostartfiles : Flag<["-"], "nostartfiles">;

cfe/trunk/include/clang/Driver/ToolChain.h

public:
   /// This checks for presence of the -Ofast, -ffast-math or -funsafe-math flags.
   virtual bool AddFastMathRuntimeIfAvailable(
       const llvm::opt::ArgList &Args, llvm::opt::ArgStringList &CmdArgs) const;
   /// addProfileRTLibs - When -fprofile-instr-profile is specified, try to pass
   /// a suitable profile runtime library to the linker.
   virtual void addProfileRTLibs(const llvm::opt::ArgList &Args,
                                 llvm::opt::ArgStringList &CmdArgs) const;
 
+  /// \brief Add arguments to use system-specific CUDA includes.
+  virtual void AddCudaIncludeArgs(const llvm::opt::ArgList &DriverArgs,
+                                  llvm::opt::ArgStringList &CC1Args) const;
+
   /// \brief Return sanitizers which are available in this toolchain.
   virtual SanitizerMask getSupportedSanitizers() const;
 };
 
 } // end namespace driver
 } // end namespace clang
 
 #endif

cfe/trunk/lib/Driver/ToolChain.cpp

SanitizerMask ToolChain::getSupportedSanitizers() const {
   using namespace SanitizerKind;
   SanitizerMask Res = (Undefined & ~Vptr & ~Function) | (CFI & ~CFIICall) |
                       CFICastStrict | UnsignedIntegerOverflow | LocalBounds;
   if (getTriple().getArch() == llvm::Triple::x86 ||
       getTriple().getArch() == llvm::Triple::x86_64)
     Res |= CFIICall;
   return Res;
 }
+
+void ToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs,
+                                   ArgStringList &CC1Args) const {}

cfe/trunk/lib/Driver/ToolChains.h

public:
   bool HasNativeLLVMSupport() const override;
 
   void
   AddClangSystemIncludeArgs(const llvm::opt::ArgList &DriverArgs,
                             llvm::opt::ArgStringList &CC1Args) const override;
   void AddClangCXXStdlibIncludeArgs(
       const llvm::opt::ArgList &DriverArgs,
       llvm::opt::ArgStringList &CC1Args) const override;
+  void AddCudaIncludeArgs(const llvm::opt::ArgList &DriverArgs,
+                          llvm::opt::ArgStringList &CC1Args) const override;
   bool isPIEDefault() const override;
   SanitizerMask getSupportedSanitizers() const override;
   void addProfileRTLibs(const llvm::opt::ArgList &Args,
                         llvm::opt::ArgStringList &CmdArgs) const override;
   virtual std::string computeSysRoot() const;
 
   std::string Linker;
   std::vector<std::string> ExtraOpts;

cfe/trunk/lib/Driver/ToolChains.cpp

for (const auto &IncludePath : LibStdCXXIncludePathCandidates) {
     if (addLibStdCXXIncludePaths(IncludePath, /*Suffix*/ "", TripleStr,
                                  /*GCCMultiarchTriple*/ "",
                                  /*TargetMultiarchTriple*/ "",
                                  Multilib.includeSuffix(), DriverArgs, CC1Args))
       break;
   }
 }
 
+void Linux::AddCudaIncludeArgs(const ArgList &DriverArgs,
+                               ArgStringList &CC1Args) const {
+  if (DriverArgs.hasArg(options::OPT_nocudainc))
+    return;
+
+  if (CudaInstallation.isValid())
+    addSystemInclude(DriverArgs, CC1Args, CudaInstallation.getIncludePath());
+}
+
 bool Linux::isPIEDefault() const { return getSanitizerArgs().requiresPIE(); }
 
 SanitizerMask Linux::getSupportedSanitizers() const {
   const bool IsX86 = getTriple().getArch() == llvm::Triple::x86;
   const bool IsX86_64 = getTriple().getArch() == llvm::Triple::x86_64;
   const bool IsMIPS64 = getTriple().getArch() == llvm::Triple::mips64 ||
                         getTriple().getArch() == llvm::Triple::mips64el;
   const bool IsPowerPC64 = getTriple().getArch() == llvm::Triple::ppc64 ||

cfe/trunk/lib/Driver/Tools.h

public:
   static const char *getDependencyFileName(const llvm::opt::ArgList &Args,
                                            const InputInfoList &Inputs);
 
 private:
   void AddPreprocessingOptions(Compilation &C, const JobAction &JA,
                                const Driver &D, const llvm::opt::ArgList &Args,
                                llvm::opt::ArgStringList &CmdArgs,
                                const InputInfo &Output,
-                               const InputInfoList &Inputs) const;
+                               const InputInfoList &Inputs,
+                               const ToolChain *AuxToolChain) const;
 
   void AddAArch64TargetArgs(const llvm::opt::ArgList &Args,
                             llvm::opt::ArgStringList &CmdArgs) const;
   void AddARMTargetArgs(const llvm::Triple &Triple,
                         const llvm::opt::ArgList &Args,
                         llvm::opt::ArgStringList &CmdArgs,
                         bool KernelOrKext) const;
   void AddARM64TargetArgs(const llvm::opt::ArgList &Args,

cfe/trunk/lib/Driver/Tools.cpp

static bool forwardToGCC(const Option &O) {
   return O.getKind() != Option::InputClass &&
          !O.hasFlag(options::DriverOption) && !O.hasFlag(options::LinkerInput);
 }
 
 void Clang::AddPreprocessingOptions(Compilation &C, const JobAction &JA,
                                     const Driver &D, const ArgList &Args,
                                     ArgStringList &CmdArgs,
                                     const InputInfo &Output,
-                                    const InputInfoList &Inputs) const {
+                                    const InputInfoList &Inputs,
+                                    const ToolChain *AuxToolChain) const {
   Arg *A;
 
   CheckPreprocessingOptions(D, Args);
 
   Args.AddLastArg(CmdArgs, options::OPT_C);
   Args.AddLastArg(CmdArgs, options::OPT_CC);
 
   // Handle dependency file generation.
void Clang::AddPreprocessingOptions(Compilation &C, const JobAction &JA,
   addDirectoryList(Args, CmdArgs, "-c-isystem", "C_INCLUDE_PATH");
   // CPLUS_INCLUDE_PATH - system includes enabled when compiling C++.
   addDirectoryList(Args, CmdArgs, "-cxx-isystem", "CPLUS_INCLUDE_PATH");
   // OBJC_INCLUDE_PATH - system includes enabled when compiling ObjC.
   addDirectoryList(Args, CmdArgs, "-objc-isystem", "OBJC_INCLUDE_PATH");
   // OBJCPLUS_INCLUDE_PATH - system includes enabled when compiling ObjC++.
   addDirectoryList(Args, CmdArgs, "-objcxx-isystem", "OBJCPLUS_INCLUDE_PATH");
 
+  // Optional AuxToolChain indicates that we need to include headers
+  // for more than one target. If that's the case, add include paths
+  // from AuxToolChain right after include paths of the same kind for
+  // the current target.
+
   // Add C++ include arguments, if needed.
-  if (types::isCXX(Inputs[0].getType()))
+  if (types::isCXX(Inputs[0].getType())) {
     getToolChain().AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
+    if (AuxToolChain)
+      AuxToolChain->AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
+  }
 
   // Add system include arguments.
   getToolChain().AddClangSystemIncludeArgs(Args, CmdArgs);
+  if (AuxToolChain)
+      AuxToolChain->AddClangCXXStdlibIncludeArgs(Args, CmdArgs);
+
+  // Add CUDA include arguments, if needed.
+  if (types::isCuda(Inputs[0].getType()))
+    getToolChain().AddCudaIncludeArgs(Args, CmdArgs);
 }
 
 // FIXME: Move to target hook.
 static bool isSignedCharDefault(const llvm::Triple &Triple) {
   switch (Triple.getArch()) {
   default:
     return true;
 
void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   //
   // FIXME: Implement custom jobs for internal actions.
   CmdArgs.push_back("-cc1");
 
   // Add the "effective" target triple.
   CmdArgs.push_back("-triple");
   CmdArgs.push_back(Args.MakeArgString(TripleStr));
 
+  const ToolChain *AuxToolChain = nullptr;
   if (IsCuda) {
     // FIXME: We need a (better) way to pass information about
     // particular compilation pass we're constructing here. For now we
     // can check which toolchain we're using and pick the other one to
     // extract the triple.
-    const ToolChain *AuxToolChain;
     if (&getToolChain() == C.getCudaDeviceToolChain())
       AuxToolChain = C.getCudaHostToolChain();
     else if (&getToolChain() == C.getCudaHostToolChain())
       AuxToolChain = C.getCudaDeviceToolChain();
     else
       llvm_unreachable("Can't figure out CUDA compilation mode.");
     assert(AuxToolChain != nullptr && "No aux toolchain.");
     CmdArgs.push_back("-aux-triple");
if (const Arg *A = Args.getLastArg(options::OPT_ccc_objcmt_migrate)) {
     Args.AddLastArg(CmdArgs, options::OPT_objcmt_whitelist_dir_path);
   }
 
   // Add preprocessing options like -I, -D, etc. if we are using the
   // preprocessor.
   //
   // FIXME: Support -fpreprocessed
   if (types::getPreprocessedType(InputType) != types::TY_INVALID)
-    AddPreprocessingOptions(C, JA, D, Args, CmdArgs, Output, Inputs);
+    AddPreprocessingOptions(C, JA, D, Args, CmdArgs, Output, Inputs,
+                            AuxToolChain);
 
   // Don't warn about "clang -c -DPIC -fPIC test.i" because libtool.m4 assumes
   // that "The compiler can only warn and ignore the option if not recognized".
   // When building with ccache, it will pass -D options to clang even on
   // preprocessed inputs and configure concludes that -fPIC is not supported.
   Args.ClaimAllArgs(options::OPT_D);
 
   // Manually translate -O4 to -O3; let clang reject others.

cfe/trunk/test/Driver/cuda-detect.cu

 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
+// REQUIRES: nvptx-registered-target
 //
+// # Check that we properly detect CUDA installation.
 // RUN: %clang -v --target=i386-unknown-linux \
-// RUN:   --sysroot=/tmp/no-cuda-there 2>&1 | FileCheck %s -check-prefix NOCUDA
+// RUN:   --sysroot=%S/no-cuda-there 2>&1 | FileCheck %s -check-prefix NOCUDA
+// RUN: %clang -v --target=i386-unknown-linux \
+// RUN:   --sysroot=%S/Inputs/CUDA 2>&1 | FileCheck %s
 // RUN: %clang -v --target=i386-unknown-linux \
 // RUN:   --cuda-path=%S/Inputs/CUDA/usr/local/cuda 2>&1 | FileCheck %s
 
+// Verify that CUDA include path gets added
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
+// RUN:   --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN:   | FileCheck %s -check-prefix COMMON -check-prefix CUDAINC
+// Verify that -nocudainc disables CUDA include paths.
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
+// RUN:   -nocudainc --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
+// RUN:   | FileCheck %s -check-prefix COMMON -check-prefix NOCUDAINC
+// We should not add any CUDA include paths if there's no valid CUDA installation
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
+// RUN:   --cuda-path=%S/no-cuda-there %s 2>&1 \
+// RUN:   | FileCheck %s -check-prefix COMMON -check-prefix NOCUDAINC
+
 // CHECK: Found CUDA installation: {{.*}}/Inputs/CUDA/usr/local/cuda
 // NOCUDA-NOT: Found CUDA installation:
+
+// COMMON: "-triple" "nvptx-nvidia-cuda"
+// COMMON-SAME: "-fcuda-is-device"
+// CUDAINC-SAME: "-internal-isystem" "{{.*}}/Inputs/CUDA/usr/local/cuda/include"
+// NOCUDAINC-NOT: "-internal-isystem" "{{.*}}/cuda/include"
+// COMMON-SAME: "-x" "cuda"
+